INDEX

Explanations

mentions of "car" or related terms

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.93

]").

-0.83

 ſeveral

-0.81

 ligiloj

-0.79

 Theſe

-0.78

)"),

-0.77

 ſmall

-0.77

 Grau

-0.76

jboss

-0.75

 Majefty

-0.75

POSITIVE LOGITS

car

1.20

Car

1.11

Car

1.08

CAR

1.08

car

1.05

CAR

1.02

 Cars

0.96

 cars

0.95

Cars

0.94

 Carney

0.87

Activations Density 0.033%

mentions of "car" or related terms

No Comments

No Known Activations

mentions of "car" or related terms

No Comments

No Known Activations